A probabilistic framework for next best view estimation in a cluttered environment.pdfVIP

J. Vis. Commun. Image R. 25 (2014) 148–164 Contents lists available at ScienceDirect J. Vis. Commun. Image R. journal homepage: /locate/jvci A probabilistic framework for next best view estimation in a cluttered environment Christian Potthast ?, Gaurav S. Sukhatme Robotic Embedded Systems Laboratory, University of Southern California, Los Angeles, CA 90089-0781, United States article info Article history: Available online 19 July 2013 Keywords: Next best view estimation Sensor placement Sensor planning View planning Robot exploration 3-D perception Cluttered environments Missing points abstract In this article, we present an information gain-based variant of the next best view problem for occluded environment. Our proposed method utilizes a belief model of the unobserved space to estimate the expected information gain of each possible viewpoint. More precise, this belief model allows a more precise estimation of the visibility of occluded space and with that a more accurate prediction of the potential information gain of new viewing positions. We present experimental evaluation on a robotic platform for active data acquisition, however due to the generality of our approach it also applies to a wide variety of 3D reconstruction problems. With the evaluation done in simulation and on a real robotic platform, exploring and acquiring data from different environments we demonstrate the generality and usefulness of our approach for next best view estimation and autonomous data acquisition. ó 2013 Elsevier Inc. All rights reserved. 1. Introduction Major research areas in computer vision and robotics are autonomous 3D data acquisition and reconstruction of dense geometry of full environments or single objects. A substantial dif?culty, and of most importance, is the selection of viewpoints for data acquisition and to accomplish subsequent tasks like reconstruction or object manipulation. Oftentimes we are limited by time, energy, or storage, but also occlusion making it nece